dinhanhx

dinhanhx

·

dinhanhx

AI & ML interests

Vision Language

Recent Activity

liked a model about 9 hours ago

PaddlePaddle/SLANeXt_wired_safetensors

liked a model about 9 hours ago

PaddlePaddle/SLANet_safetensors

liked a model 4 days ago

LiquidAI/LFM2.5-Encoder-350M

View all activity

Organizations

upvoted a paper 27 days ago

MiniCPM4: Ultra-Efficient LLMs on End Devices

Paper • 2506.07900 • Published Jun 9, 2025 • 101

upvoted 2 articles 27 days ago

Article

Training and Finetuning Sparse Embedding Models with Sentence Transformers

tomaarsen, arthurbresnu

•

Jul 1, 2025

• 140

Article

Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers

tomaarsen

•

Aug 26

• 144

upvoted an article about 1 month ago

Article

Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps

+1

iamleonie, burtenshaw, sergiopaniego

•

Sep 3

• 147

upvoted a collection 2 months ago

Laguna XS 2.1

Designed for agentic coding and long-horizon work on a local machine. Licensed under OpenMDW-1.1. • 9 items • Updated Jul 2 • 25

upvoted a collection 3 months ago

LingBot-Vision

5 items • Updated Jul 7 • 11

upvoted a collection 4 months ago

Gemma 4 QAT Q4_0

19 items • Updated Jul 21 • 162

upvoted a paper 5 months ago

SAM3-LiteText: An Anatomical Study of the SAM3 Text Encoder for Efficient Vision-Language Segmentation

Paper • 2602.12173 • Published Feb 12 • 3

upvoted an article 6 months ago

Article

Running Native PyTorch on TPUs with Zero Code Changes

rishiraj

•

Feb 21

• 6

upvoted a paper 6 months ago

SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Paper • 2502.14786 • Published Feb 20, 2025 • 169

upvoted an article 6 months ago

Article

Welcome Gemma 4: Frontier multimodal intelligence on device

+5

merve, pcuenq, sergiopaniego, burtenshaw, Steveeeeeeen, alvarobartt, SaylorTwift

•

Apr 2

• 930

upvoted a collection 6 months ago

jina-embeddings-v5-text

Our 5th-gen embeddings: two lightweight multilingual models with SOTA performance in retrieval, matching, clustering, and classification. • 29 items • Updated 20 days ago • 42

upvoted a collection 7 months ago

NVIDIA Nemotron v3

Open, Production-ready Enterprise Models • 33 items • Updated Aug 14 • 379

upvoted an article 8 months ago

Article

ViDoRe V3: a comprehensive evaluation of retrieval for enterprise use-cases

QuentinJG

•

Nov 5, 2025

• 68

upvoted a collection 8 months ago

Contextual AI Reranker v2

Family of instruction-following multilingual rerankers on the cost/performance Pareto frontier across public and customer benchmarks • 9 items • Updated Apr 23 • 12

upvoted a paper 8 months ago

LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding

Paper • 2202.13669 • Published Feb 28, 2022 • 3

upvoted an article 9 months ago

Article

How We Built a Semantic Highlight Model To Save Token Cost for RAG

zilliz

•

Jan 15

• 67

upvoted a paper 10 months ago

NV-Retriever: Improving text embedding models with effective hard-negative mining

Paper • 2407.15831 • Published Jul 22, 2024 • 6

upvoted a collection 10 months ago

Pixio

5 items • Updated Dec 19, 2025 • 17

upvoted a collection 11 months ago

DRAMA

A collection of small (sub-1B) multilingual dense retrievers that generalize well across a number of tasks and languages. • 3 items • Updated Feb 26, 2025 • 9